© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77954
    Prev
    Next
    INDEX
    Explanations

    code comments and headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     entire
    -0.82
     (...)
    -0.81
    達の
    -0.80
     adaptarse
    -0.75
     repressed
    -0.74
     phê
    -0.73
    ների
    -0.72
     celebró
    -0.71
     verá
    -0.71
     entirety
    -0.71
    POSITIVE LOGITS
       
    4.31
        
    1.65
         
    1.57
           
    1.22
    )　
    1.14
    ）　
    1.09
    quad
    1.08
     
    1.05
               
    1.05
      
    1.04
    Activations Density 0.371%

    No Known Activations